From d7b74a4c56d720d1ce914fdcaccb8fc7fb2d4ba5 Mon Sep 17 00:00:00 2001 From: AnnaXWang <6621137+AnnaXWang@users.noreply.github.com> Date: Mon, 29 Jun 2026 23:19:21 +0000 Subject: [PATCH 1/8] Add Computer Use overview page Introduce a landing page for the Computer Use integrations group that explains the screenshot action-observation loop, links each supported model, and points to the Computer Controls API. Wire it in as the first page of the group and redirect the bare section path to it. --- docs.json | 2 + integrations/computer-use/overview.mdx | 71 ++++++++++++++++++++++++++ 2 files changed, 73 insertions(+) create mode 100644 integrations/computer-use/overview.mdx diff --git a/docs.json b/docs.json index 5bcd2ec4..a06c9528 100644 --- a/docs.json +++ b/docs.json @@ -11,6 +11,7 @@ { "source": "/auth/agent/programmatic", "destination": "/auth/programmatic" }, { "source": "/auth/agent/faq", "destination": "/auth/faq" }, { "source": "/browsers/hardware-acceleration", "destination": "/browsers/gpu-acceleration" }, + { "source": "/integrations/computer-use", "destination": "/integrations/computer-use/overview" }, { "source": "/browsers/create-a-browser", "destination": "/introduction/create" }, { "source": "/introduction", "destination": "/" }, { "source": "/quickstart", "destination": "/" }, @@ -206,6 +207,7 @@ { "group": "Computer Use", "pages": [ + "integrations/computer-use/overview", "integrations/computer-use/anthropic", "integrations/computer-use/gemini", "integrations/computer-use/openagi", diff --git a/integrations/computer-use/overview.mdx b/integrations/computer-use/overview.mdx new file mode 100644 index 00000000..06bb5448 --- /dev/null +++ b/integrations/computer-use/overview.mdx @@ -0,0 +1,71 @@ +--- +title: "Overview" +description: "Run screenshot-driven computer use agents on Kernel cloud browsers" +--- + +Computer use models are vision-language models (VLMs) that operate a browser the way a person does: they look at a screenshot, decide what to do next, and emit a concrete action—move the mouse, click, type, scroll, or drag. Kernel runs these agents on cloud browsers, so you don't install or maintain anything locally, and gives the model the low-level [Computer Controls API](/browsers/computer-controls) it needs to see the screen and act on it. + +## How computer use works on Kernel + +Every computer use integration runs the same action-observation loop: + +1. **Capture** a screenshot of the current browser state with the [Computer Controls API](/browsers/computer-controls). +2. **Predict** the next action by sending that screenshot to your model. +3. **Execute** the returned action—click, type, scroll, drag, or key press—through Computer Controls. +4. **Repeat** until the task is complete. + +Computer Controls emulates native keyboard and mouse input at the OS level—with human-like [Bézier curves](/browsers/computer-controls#move-the-mouse) by default—instead of driving the page over the Chrome DevTools Protocol (CDP). This keeps the loop close to real user input and reduces the automation signals that [bot detection](/browsers/bot-detection/overview) systems look for. + +The loop works with any VLM that predicts actions from pixels. The models below are the ones we maintain ready-to-deploy templates and guides for. + +## Supported models + + + + Claude's computer use tool + + + Google's Gemini 2.5 Computer Use model + + + OpenAGI's Lux model + + + OpenAI's computer-using agent (CUA) + + + Tzafon's Northstar CUA Fast model + + + Yutori's Navigator n1.5 pixels-to-actions model + + + +Using a model that isn't listed here? Any VLM works—wire its predicted actions straight to the [Computer Controls API](/browsers/computer-controls) and run the same loop. + +## Get started + +Each model page includes a one-command template so you can deploy a working agent in minutes. For example, to scaffold the Anthropic integration: + +```bash +kernel create --name my-computer-use-app --template computer-use +``` + +Pick a model above to get its template, then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to run your agent on Kernel. + +## Benefits of using Kernel for computer use + +- **No local browser management**: Run computer use automations without installing or maintaining browsers locally +- **Scalability**: Launch multiple browser sessions in parallel for concurrent AI agents +- **Stealth mode**: Built-in anti-detection features for reliable web interactions +- **Session state**: Maintain browser state across runs via [Profiles](/auth/profiles) +- **Live view**: Debug your agents with real-time browser viewing +- **Cloud infrastructure**: Run computationally intensive AI agents without local resource constraints + +## Next steps + +- Read the [Computer Controls API](/browsers/computer-controls) reference for the full set of mouse, keyboard, and screenshot actions +- Check out [live view](/browsers/live-view) for debugging your automations +- Learn about [stealth mode](/browsers/bot-detection/stealth) for avoiding detection +- Learn how to properly [terminate browser sessions](/browsers/termination) +- Learn how to [deploy](/apps/deploy) your computer use app to Kernel From 96e32c07b6b411147dcca1ae9e5ec8dbf241f260 Mon Sep 17 00:00:00 2001 From: Anna Wang Date: Mon, 29 Jun 2026 18:03:39 -0700 Subject: [PATCH 2/8] Apply suggestion from @AnnaXWang --- integrations/computer-use/overview.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/integrations/computer-use/overview.mdx b/integrations/computer-use/overview.mdx index 06bb5448..4ae36755 100644 --- a/integrations/computer-use/overview.mdx +++ b/integrations/computer-use/overview.mdx @@ -1,6 +1,6 @@ --- title: "Overview" -description: "Run screenshot-driven computer use agents on Kernel cloud browsers" +description: "Run computer use agents on Kernel cloud browsers" --- Computer use models are vision-language models (VLMs) that operate a browser the way a person does: they look at a screenshot, decide what to do next, and emit a concrete action—move the mouse, click, type, scroll, or drag. Kernel runs these agents on cloud browsers, so you don't install or maintain anything locally, and gives the model the low-level [Computer Controls API](/browsers/computer-controls) it needs to see the screen and act on it. From 3780ea9f5a0fadf3a7f00990dcba6fa28df4d7da Mon Sep 17 00:00:00 2001 From: Anna Wang Date: Tue, 30 Jun 2026 09:14:30 -0700 Subject: [PATCH 3/8] Apply suggestion from @AnnaXWang --- integrations/computer-use/overview.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/integrations/computer-use/overview.mdx b/integrations/computer-use/overview.mdx index 4ae36755..e246f472 100644 --- a/integrations/computer-use/overview.mdx +++ b/integrations/computer-use/overview.mdx @@ -3,7 +3,7 @@ title: "Overview" description: "Run computer use agents on Kernel cloud browsers" --- -Computer use models are vision-language models (VLMs) that operate a browser the way a person does: they look at a screenshot, decide what to do next, and emit a concrete action—move the mouse, click, type, scroll, or drag. Kernel runs these agents on cloud browsers, so you don't install or maintain anything locally, and gives the model the low-level [Computer Controls API](/browsers/computer-controls) it needs to see the screen and act on it. +Computer use models are vision-language models (VLMs) that operate a browser the way a person does: they look at a screenshot, decide what to do next, and emit a concrete action—move the mouse, click, type, scroll, or drag. Kernel runs these agents on cloud browsers, so you don't install or maintain anything locally, and gives the model the low-level [Computer Controls API](/browsers/computer-controls#take-screenshots) it needs to see the screen and act on it. ## How computer use works on Kernel From 4f00c550ecba52140ef87e6b7b761b7b807dd533 Mon Sep 17 00:00:00 2001 From: AnnaXWang <6621137+AnnaXWang@users.noreply.github.com> Date: Tue, 30 Jun 2026 16:21:41 +0000 Subject: [PATCH 4/8] Replace em-dashes with colons, parentheses, and semicolons --- integrations/computer-use/overview.mdx | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/integrations/computer-use/overview.mdx b/integrations/computer-use/overview.mdx index e246f472..3de57885 100644 --- a/integrations/computer-use/overview.mdx +++ b/integrations/computer-use/overview.mdx @@ -3,7 +3,7 @@ title: "Overview" description: "Run computer use agents on Kernel cloud browsers" --- -Computer use models are vision-language models (VLMs) that operate a browser the way a person does: they look at a screenshot, decide what to do next, and emit a concrete action—move the mouse, click, type, scroll, or drag. Kernel runs these agents on cloud browsers, so you don't install or maintain anything locally, and gives the model the low-level [Computer Controls API](/browsers/computer-controls#take-screenshots) it needs to see the screen and act on it. +Computer use models are vision-language models (VLMs) that operate a browser the way a person does: they look at a screenshot, decide what to do next, and emit a concrete action: move the mouse, click, type, scroll, or drag. Kernel runs these agents on cloud browsers, so you don't install or maintain anything locally, and gives the model the low-level [Computer Controls API](/browsers/computer-controls#take-screenshots) it needs to see the screen and act on it. ## How computer use works on Kernel @@ -11,10 +11,10 @@ Every computer use integration runs the same action-observation loop: 1. **Capture** a screenshot of the current browser state with the [Computer Controls API](/browsers/computer-controls). 2. **Predict** the next action by sending that screenshot to your model. -3. **Execute** the returned action—click, type, scroll, drag, or key press—through Computer Controls. +3. **Execute** the returned action (click, type, scroll, drag, or key press) through Computer Controls. 4. **Repeat** until the task is complete. -Computer Controls emulates native keyboard and mouse input at the OS level—with human-like [Bézier curves](/browsers/computer-controls#move-the-mouse) by default—instead of driving the page over the Chrome DevTools Protocol (CDP). This keeps the loop close to real user input and reduces the automation signals that [bot detection](/browsers/bot-detection/overview) systems look for. +Computer Controls emulates native keyboard and mouse input at the OS level (with human-like [Bézier curves](/browsers/computer-controls#move-the-mouse) by default) instead of driving the page over the Chrome DevTools Protocol (CDP). This keeps the loop close to real user input and reduces the automation signals that [bot detection](/browsers/bot-detection/overview) systems look for. The loop works with any VLM that predicts actions from pixels. The models below are the ones we maintain ready-to-deploy templates and guides for. @@ -41,7 +41,7 @@ The loop works with any VLM that predicts actions from pixels. The models below -Using a model that isn't listed here? Any VLM works—wire its predicted actions straight to the [Computer Controls API](/browsers/computer-controls) and run the same loop. +Using a model that isn't listed here? Any VLM works; wire its predicted actions straight to the [Computer Controls API](/browsers/computer-controls) and run the same loop. ## Get started From 3393a5e05507dc46d94974d696b131fed8b4cffc Mon Sep 17 00:00:00 2001 From: AnnaXWang <6621137+AnnaXWang@users.noreply.github.com> Date: Tue, 30 Jun 2026 16:32:10 +0000 Subject: [PATCH 5/8] Add cua-agent build-your-own-agent guide Document the @onkernel/cua-agent library path in the Computer Use overview with an install, a starter snippet, and a provider/model-ref table, and cross-link it from each cua-supported provider page. --- integrations/computer-use/anthropic.mdx | 2 ++ integrations/computer-use/gemini.mdx | 2 ++ integrations/computer-use/openai.mdx | 2 ++ integrations/computer-use/overview.mdx | 39 +++++++++++++++++++++++++ integrations/computer-use/tzafon.mdx | 2 ++ integrations/computer-use/yutori.mdx | 2 ++ 6 files changed, 49 insertions(+) diff --git a/integrations/computer-use/anthropic.mdx b/integrations/computer-use/anthropic.mdx index e6bd4a79..09206a3a 100644 --- a/integrations/computer-use/anthropic.mdx +++ b/integrations/computer-use/anthropic.mdx @@ -18,6 +18,8 @@ Choose `TypeScript` or `Python` as the programming language. Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Computer Use automation on Kernel's infrastructure. +Building your own agent? Drive Claude from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent) using the model ref `anthropic:claude-opus-4-7`. + ## Benefits of using Kernel with Computer Use - **No local browser management**: Run Computer Use automations without installing or maintaining browsers locally diff --git a/integrations/computer-use/gemini.mdx b/integrations/computer-use/gemini.mdx index 1de6ef46..af8ab3e7 100644 --- a/integrations/computer-use/gemini.mdx +++ b/integrations/computer-use/gemini.mdx @@ -16,6 +16,8 @@ kernel create --name my-computer-use-app --language typescript --template gemini Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Computer Use automation on Kernel's infrastructure. +Building your own agent? Drive Gemini from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent) using the model ref `google:gemini-3-flash-preview`. + ## Benefits of using Kernel with Computer Use - **No local browser management**: Run Computer Use automations without installing or maintaining browsers locally diff --git a/integrations/computer-use/openai.mdx b/integrations/computer-use/openai.mdx index 4c204234..c516acba 100644 --- a/integrations/computer-use/openai.mdx +++ b/integrations/computer-use/openai.mdx @@ -18,6 +18,8 @@ Choose `TypeScript` or `Python` as the programming language. Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Computer Use automation on Kernel's infrastructure. +Building your own agent? Drive OpenAI's CUA from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent) using the model ref `openai:gpt-5.5`. + ## Benefits of using Kernel with Computer Use - **No local browser management**: Run Computer Use automations without installing or maintaining browsers locally diff --git a/integrations/computer-use/overview.mdx b/integrations/computer-use/overview.mdx index 3de57885..82e9e5c9 100644 --- a/integrations/computer-use/overview.mdx +++ b/integrations/computer-use/overview.mdx @@ -53,6 +53,45 @@ kernel create --name my-computer-use-app --template computer-use Pick a model above to get its template, then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to run your agent on Kernel. +## Build your own agent + +For full control over the loop, [`@onkernel/cua-agent`](https://github.com/kernel/cua/tree/main/packages/agent) is a TypeScript library that runs it against a Kernel browser for you. You point it at a model, give it a task, and it handles the screenshots, actions, and follow-up turns. + +```bash +npm install @onkernel/cua-agent @onkernel/cua-ai @onkernel/sdk +``` + +```ts +import Kernel from "@onkernel/sdk"; +import { CuaAgent } from "@onkernel/cua-agent"; + +const client = new Kernel({ apiKey: process.env.KERNEL_API_KEY! }); +const browser = await client.browsers.create({ stealth: true }); + +const agent = new CuaAgent({ + browser, + client, + initialState: { + model: "anthropic:claude-opus-4-7", // swap to target another provider + systemPrompt: "You are a careful browser automation agent.", + }, +}); + +await agent.prompt("Open news.ycombinator.com and summarize the top story."); +``` + +Switch providers by changing the `model` ref: + +| Provider | Model ref | +| --- | --- | +| Anthropic | `anthropic:claude-opus-4-7` | +| OpenAI | `openai:gpt-5.5` | +| Gemini | `google:gemini-3-flash-preview` | +| Tzafon | `tzafon:tzafon.northstar-cua-fast` | +| Yutori | `yutori:n1.5-latest` | + +Set the matching provider key (`ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `GOOGLE_API_KEY`, `TZAFON_API_KEY`, or `YUTORI_API_KEY`) alongside `KERNEL_API_KEY`. + ## Benefits of using Kernel for computer use - **No local browser management**: Run computer use automations without installing or maintaining browsers locally diff --git a/integrations/computer-use/tzafon.mdx b/integrations/computer-use/tzafon.mdx index ca7bb14a..7490d414 100644 --- a/integrations/computer-use/tzafon.mdx +++ b/integrations/computer-use/tzafon.mdx @@ -18,6 +18,8 @@ Choose `TypeScript` or `Python` as the programming language. Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Tzafon automation on Kernel's infrastructure. +Building your own agent? Drive Northstar CUA Fast from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent) using the model ref `tzafon:tzafon.northstar-cua-fast`. + ## Benefits of using Kernel with Tzafon Northstar CUA Fast - **No local browser management**: Run Northstar CUA Fast automations without installing or maintaining browsers locally diff --git a/integrations/computer-use/yutori.mdx b/integrations/computer-use/yutori.mdx index 6f6e20ad..4b24c1ce 100644 --- a/integrations/computer-use/yutori.mdx +++ b/integrations/computer-use/yutori.mdx @@ -18,6 +18,8 @@ Choose `TypeScript` or `Python` as the programming language. Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Yutori automation on Kernel's infrastructure. +Building your own agent? Drive Navigator n1.5 from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent) using the model ref `yutori:n1.5-latest`. + ## Benefits of using Kernel with Yutori n1.5 - **No local browser management**: Run n1.5 automations without installing or maintaining browsers locally From fe1b639c1be14dce57462c1962f0d7e9025905b8 Mon Sep 17 00:00:00 2001 From: Anna Wang Date: Tue, 30 Jun 2026 09:36:14 -0700 Subject: [PATCH 6/8] Apply suggestions from code review Co-authored-by: Anna Wang --- integrations/computer-use/overview.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/integrations/computer-use/overview.mdx b/integrations/computer-use/overview.mdx index 82e9e5c9..731cb6fd 100644 --- a/integrations/computer-use/overview.mdx +++ b/integrations/computer-use/overview.mdx @@ -3,13 +3,13 @@ title: "Overview" description: "Run computer use agents on Kernel cloud browsers" --- -Computer use models are vision-language models (VLMs) that operate a browser the way a person does: they look at a screenshot, decide what to do next, and emit a concrete action: move the mouse, click, type, scroll, or drag. Kernel runs these agents on cloud browsers, so you don't install or maintain anything locally, and gives the model the low-level [Computer Controls API](/browsers/computer-controls#take-screenshots) it needs to see the screen and act on it. +Computer use models are vision-language models (VLMs) that operate a browser the way a person does: they look at a screenshot, decide what to do next, and emit a concrete action: move the mouse, click, type, scroll, or drag. Kernel runs these agents on cloud browsers, so you don't install or maintain anything locally, and gives the model the low-level [Computer Controls API](/browsers/computer-controls) it needs to see the screen and act on it. ## How computer use works on Kernel Every computer use integration runs the same action-observation loop: -1. **Capture** a screenshot of the current browser state with the [Computer Controls API](/browsers/computer-controls). +1. **Capture** a screenshot of the current browser state with the [Computer Controls API](/browsers/computer-controls#take-screenshots). 2. **Predict** the next action by sending that screenshot to your model. 3. **Execute** the returned action (click, type, scroll, drag, or key press) through Computer Controls. 4. **Repeat** until the task is complete. From 3cad613a3db34432801a5e39db0082a8e3350490 Mon Sep 17 00:00:00 2001 From: AnnaXWang <6621137+AnnaXWang@users.noreply.github.com> Date: Tue, 30 Jun 2026 17:40:46 +0000 Subject: [PATCH 7/8] Add per-provider cua-agent snippets Replace the cross-link one-liner on each cua-supported provider page with a provider-specific CuaAgent starter snippet; install instructions stay in the overview. --- integrations/computer-use/anthropic.mdx | 23 ++++++++++++++++++++++- integrations/computer-use/gemini.mdx | 23 ++++++++++++++++++++++- integrations/computer-use/openai.mdx | 23 ++++++++++++++++++++++- integrations/computer-use/tzafon.mdx | 23 ++++++++++++++++++++++- integrations/computer-use/yutori.mdx | 23 ++++++++++++++++++++++- 5 files changed, 110 insertions(+), 5 deletions(-) diff --git a/integrations/computer-use/anthropic.mdx b/integrations/computer-use/anthropic.mdx index 09206a3a..b6c5467b 100644 --- a/integrations/computer-use/anthropic.mdx +++ b/integrations/computer-use/anthropic.mdx @@ -18,7 +18,28 @@ Choose `TypeScript` or `Python` as the programming language. Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Computer Use automation on Kernel's infrastructure. -Building your own agent? Drive Claude from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent) using the model ref `anthropic:claude-opus-4-7`. +## Build your own agent + +For full control over the loop, drive Claude from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent): + +```ts +import Kernel from "@onkernel/sdk"; +import { CuaAgent } from "@onkernel/cua-agent"; + +const client = new Kernel({ apiKey: process.env.KERNEL_API_KEY! }); +const browser = await client.browsers.create({ stealth: true }); + +const agent = new CuaAgent({ + browser, + client, + initialState: { + model: "anthropic:claude-opus-4-7", + systemPrompt: "You are a careful browser automation agent.", + }, +}); + +await agent.prompt("Open news.ycombinator.com and summarize the top story."); +``` ## Benefits of using Kernel with Computer Use diff --git a/integrations/computer-use/gemini.mdx b/integrations/computer-use/gemini.mdx index af8ab3e7..bec638b1 100644 --- a/integrations/computer-use/gemini.mdx +++ b/integrations/computer-use/gemini.mdx @@ -16,7 +16,28 @@ kernel create --name my-computer-use-app --language typescript --template gemini Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Computer Use automation on Kernel's infrastructure. -Building your own agent? Drive Gemini from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent) using the model ref `google:gemini-3-flash-preview`. +## Build your own agent + +For full control over the loop, drive Gemini from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent): + +```ts +import Kernel from "@onkernel/sdk"; +import { CuaAgent } from "@onkernel/cua-agent"; + +const client = new Kernel({ apiKey: process.env.KERNEL_API_KEY! }); +const browser = await client.browsers.create({ stealth: true }); + +const agent = new CuaAgent({ + browser, + client, + initialState: { + model: "google:gemini-3-flash-preview", + systemPrompt: "You are a careful browser automation agent.", + }, +}); + +await agent.prompt("Open news.ycombinator.com and summarize the top story."); +``` ## Benefits of using Kernel with Computer Use diff --git a/integrations/computer-use/openai.mdx b/integrations/computer-use/openai.mdx index c516acba..48c629cd 100644 --- a/integrations/computer-use/openai.mdx +++ b/integrations/computer-use/openai.mdx @@ -18,7 +18,28 @@ Choose `TypeScript` or `Python` as the programming language. Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Computer Use automation on Kernel's infrastructure. -Building your own agent? Drive OpenAI's CUA from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent) using the model ref `openai:gpt-5.5`. +## Build your own agent + +For full control over the loop, drive OpenAI's CUA from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent): + +```ts +import Kernel from "@onkernel/sdk"; +import { CuaAgent } from "@onkernel/cua-agent"; + +const client = new Kernel({ apiKey: process.env.KERNEL_API_KEY! }); +const browser = await client.browsers.create({ stealth: true }); + +const agent = new CuaAgent({ + browser, + client, + initialState: { + model: "openai:gpt-5.5", + systemPrompt: "You are a careful browser automation agent.", + }, +}); + +await agent.prompt("Open news.ycombinator.com and summarize the top story."); +``` ## Benefits of using Kernel with Computer Use diff --git a/integrations/computer-use/tzafon.mdx b/integrations/computer-use/tzafon.mdx index 7490d414..4e4b6872 100644 --- a/integrations/computer-use/tzafon.mdx +++ b/integrations/computer-use/tzafon.mdx @@ -18,7 +18,28 @@ Choose `TypeScript` or `Python` as the programming language. Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Tzafon automation on Kernel's infrastructure. -Building your own agent? Drive Northstar CUA Fast from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent) using the model ref `tzafon:tzafon.northstar-cua-fast`. +## Build your own agent + +For full control over the loop, drive Northstar CUA Fast from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent): + +```ts +import Kernel from "@onkernel/sdk"; +import { CuaAgent } from "@onkernel/cua-agent"; + +const client = new Kernel({ apiKey: process.env.KERNEL_API_KEY! }); +const browser = await client.browsers.create({ stealth: true }); + +const agent = new CuaAgent({ + browser, + client, + initialState: { + model: "tzafon:tzafon.northstar-cua-fast", + systemPrompt: "You are a careful browser automation agent.", + }, +}); + +await agent.prompt("Open news.ycombinator.com and summarize the top story."); +``` ## Benefits of using Kernel with Tzafon Northstar CUA Fast diff --git a/integrations/computer-use/yutori.mdx b/integrations/computer-use/yutori.mdx index 4b24c1ce..dbb90bbd 100644 --- a/integrations/computer-use/yutori.mdx +++ b/integrations/computer-use/yutori.mdx @@ -18,7 +18,28 @@ Choose `TypeScript` or `Python` as the programming language. Then follow the [deploy](/apps/deploy) and [invoke](/apps/invoke) guides to deploy and run your Yutori automation on Kernel's infrastructure. -Building your own agent? Drive Navigator n1.5 from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent) using the model ref `yutori:n1.5-latest`. +## Build your own agent + +For full control over the loop, drive Navigator n1.5 from TypeScript with [`@onkernel/cua-agent`](/integrations/computer-use/overview#build-your-own-agent): + +```ts +import Kernel from "@onkernel/sdk"; +import { CuaAgent } from "@onkernel/cua-agent"; + +const client = new Kernel({ apiKey: process.env.KERNEL_API_KEY! }); +const browser = await client.browsers.create({ stealth: true }); + +const agent = new CuaAgent({ + browser, + client, + initialState: { + model: "yutori:n1.5-latest", + systemPrompt: "You are a careful browser automation agent.", + }, +}); + +await agent.prompt("Open news.ycombinator.com and summarize the top story."); +``` ## Benefits of using Kernel with Yutori n1.5 From 35bf54b7fde9519c11e8847fbdcc1cc8c11f7e29 Mon Sep 17 00:00:00 2001 From: AnnaXWang <6621137+AnnaXWang@users.noreply.github.com> Date: Tue, 30 Jun 2026 17:50:07 +0000 Subject: [PATCH 8/8] Remove em-dashes from OpenAI and Gemini intros --- integrations/computer-use/gemini.mdx | 2 +- integrations/computer-use/openai.mdx | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/integrations/computer-use/gemini.mdx b/integrations/computer-use/gemini.mdx index bec638b1..3403e3c0 100644 --- a/integrations/computer-use/gemini.mdx +++ b/integrations/computer-use/gemini.mdx @@ -2,7 +2,7 @@ title: "Gemini" --- -[Gemini 2.5 Computer Use](https://blog.google/technology/google-deepmind/gemini-computer-use-model/) is Google's groundbreaking capability that enables AI models to interact with computers the way humans do—by looking at screens, moving cursors, clicking buttons, and typing text. This powerful feature allows AI agents to control web browsers, navigate interfaces, and perform complex tasks across applications. +[Gemini 2.5 Computer Use](https://blog.google/technology/google-deepmind/gemini-computer-use-model/) is Google's groundbreaking capability that enables AI models to interact with computers the way humans do by looking at screens, moving cursors, clicking buttons, and typing text. This powerful feature allows AI agents to control web browsers, navigate interfaces, and perform complex tasks across applications. By integrating Gemini 2.5 Computer Use with Kernel, you can run these AI-powered browser automations on cloud-hosted infrastructure, eliminating the need for local browser management and enabling scalable, reliable AI agents. diff --git a/integrations/computer-use/openai.mdx b/integrations/computer-use/openai.mdx index 48c629cd..1cd249a8 100644 --- a/integrations/computer-use/openai.mdx +++ b/integrations/computer-use/openai.mdx @@ -2,7 +2,7 @@ title: "OpenAI" --- -[Computer Use](https://openai.com/index/computer-using-agent/) is OpenAI's feature that enables AI models to interact with computers the way humans do—by looking at screens, moving cursors, clicking buttons, and typing text. This powerful feature allows AI agents to control web browsers, navigate interfaces, and perform complex tasks across applications. +[Computer Use](https://openai.com/index/computer-using-agent/) is OpenAI's feature that enables AI models to interact with computers the way humans do by looking at screens, moving cursors, clicking buttons, and typing text. This powerful feature allows AI agents to control web browsers, navigate interfaces, and perform complex tasks across applications. By integrating Computer Use with Kernel, you can run these AI-powered browser automations on cloud-hosted infrastructure, eliminating the need for local browser management and enabling scalable, reliable AI agents.